Thread: [mpls-linux-general] Benchmarking mpls problems !?
Status: Beta
Brought to you by:
jleu
Menu
▾
▴
mpls-linux-general
|
From: Sasa P. <sas...@fe...> - 2005-03-14 09:52:46
Attachments:
network
|
Did anyone tested MPLS network with netperf, netpipe, ping or some other
network tool, becouse I had some problems with measuring MPLS throughput
and round-trip-time.
Network:
Source Ingress
Ingress Destination
Egress
Egress
--------- --------- --------- ---------
--------- --------- ---------
| ip
|--------|ip/mpls|--------|ip/mpls|--------|ip/mpls|--------|ip/mpls|--------|ip/mpls|-------
| ip |
| node | | node 1| | node 2| | node 3| |
node 4| | node 5| | node |
--------- --------- --------- ---------
--------- --------- ---------
| |
|
| |
|
| |
|
--------- ---------
---------
|ip/mpls|-------------------------|ip/mpls|-------------------------|ip/mpls|
| node 6| | node 7|
| node 8|
--------- ---------
---------
All nodes are connected with 100 Mbps links.
I try to compare IP and MPLS throughput and RTT, but I got odd results.
For IP throughput between Source and Destination with netperf, I got
approximately 90 Mbps over 1,2,3,4 and 5 mpls node, but for MPLS
throughput with same tool I got only 350 kbps.
When I ping (ping -qfc 10000 -s 8 dest_ip) Destination from Source, for
MPLS I got 100 times bigger min/avg/max RTT resutls then for IP. But
for MPLS is faster total ping time then for IP.
One more problem: Why IP TTL is decrementing when transmitting thruogh
MPLS network. I think that IP TTL must be unchanged in MPLS network.
|
|
From: Christophe F. <cf...@ut...> - 2005-03-14 10:09:14
|
On Mon, 14 Mar 2005, Sasa Pavlek wrote: > One more problem: Why IP TTL is decrementing when transmitting thruogh MPLS > network. I think that IP TTL must be unchanged in MPLS network. At ingress, the IP TTL is copied into MPLS TTL. At egress, the MPLS TTL is copied into the IP TTL. -- Christophe Fillot (cf...@ut...) | Universite de Technologie de Compiegne Tel: (+33) 03.44.23.79.02 | Service Informatique - Ingenieur Reseaux GSM: (+33) 06.70.50.24.55 | Centre de Recherche de Royallieu Fax: (+33) 03.44.23.46.77 | BP 20.529, 60205 Compiegne Cedex |
|
From: sasa p. <sp...@pi...> - 2005-03-14 11:17:13
|
May be I didn't be enough specific. I was monitoring MPLS traffic on every LSR and TTL is decrementing every MPLS hop. On Mon, 14 Mar 2005, Christophe Fillot wrote: > On Mon, 14 Mar 2005, Sasa Pavlek wrote: > > > One more problem: Why IP TTL is decrementing when transmitting thruogh MPLS > > network. I think that IP TTL must be unchanged in MPLS network. > > At ingress, the IP TTL is copied into MPLS TTL. At egress, the MPLS TTL > is copied into the IP TTL. > > -- > Christophe Fillot (cf...@ut...) | Universite de Technologie de Compiegne > Tel: (+33) 03.44.23.79.02 | Service Informatique - Ingenieur Reseaux > GSM: (+33) 06.70.50.24.55 | Centre de Recherche de Royallieu > Fax: (+33) 03.44.23.46.77 | BP 20.529, 60205 Compiegne Cedex > > |
|
From: James R. L. <jl...@mi...> - 2005-03-14 19:47:46
|
On Mon, Mar 14, 2005 at 12:17:02PM +0100, sasa pavlek wrote: > May be I didn't be enough specific. I was monitoring MPLS > traffic on every LSR and TTL is decrementing every MPLS hop. Yes the MPLS TTL _is_ decremented at every hop that is the whole point of i= t. If your refering to the IP TTL being changed at every hop, then your network is configured wrong, and you did not cross connect the ILM and NHLFE, in other words you created a bunch of single hop LSPs that result in L3 lookups at every hop. How are you creating the LSPs? Did you try using quagga-mpls? It has a CLI for creating static LSPs that might be easier for you to use. > On Mon, 14 Mar 2005, Christophe Fillot wrote: >=20 > > On Mon, 14 Mar 2005, Sasa Pavlek wrote: > > > > > One more problem: Why IP TTL is decrementing when transmitting thruog= h MPLS > > > network. I think that IP TTL must be unchanged in MPLS network. > > > > At ingress, the IP TTL is copied into MPLS TTL. At egress, the MPLS TTL > > is copied into the IP TTL. > > > > -- > > Christophe Fillot (cf...@ut...) | Universite de Technologie de Compiegne > > Tel: (+33) 03.44.23.79.02 | Service Informatique - Ingenieur Reseaux > > GSM: (+33) 06.70.50.24.55 | Centre de Recherche de Royallieu > > Fax: (+33) 03.44.23.46.77 | BP 20.529, 60205 Compiegne Cedex > > > > >=20 >=20 >=20 > ------------------------------------------------------- > SF email is sponsored by - The IT Product Guide > Read honest & candid reviews on hundreds of IT Products from real users. > Discover which products truly live up to the hype. Start reading now. > http://ads.osdn.com/?ad_id=3D6595&alloc_id=3D14396&op=3Dclick > _______________________________________________ > mpls-linux-general mailing list > mpl...@li... > https://lists.sourceforge.net/lists/listinfo/mpls-linux-general --=20 James R. Leu jl...@mi... |
|
From: James R. L. <jl...@mi...> - 2005-03-14 19:12:49
|
On Mon, Mar 14, 2005 at 10:56:46AM +0100, Sasa Pavlek wrote: > Did anyone tested MPLS network with netperf, netpipe, ping or some other= =20 > network tool, becouse I had some problems with measuring MPLS throughput= =20 > and round-trip-time. mpls-linux is not optimized for throughput it is optimized for flexibility and correctness, you would have seen that had you searched the mailing list archives. I would be happy to work with someone if they would like to try and optimize mpls-linux for throughput. > Network: >=20 > Source Ingress = =20 > Ingress Destination > Egress =20 > Egress =20 > =20 > --------- --------- --------- --------- =20 > --------- --------- --------- > | ip =20 > |--------|ip/mpls|--------|ip/mpls|--------|ip/mpls|--------|ip/mpls|----= ----|ip/mpls|-------=20 > | ip | > | node | | node 1| | node 2| | node 3| |=20 > node 4| | node 5| | node | > --------- --------- --------- --------- =20 > --------- --------- --------- > | | =20 > | > | | =20 > | > | | =20 > | > --------- --------- =20 > --------- > =20 > |ip/mpls|-------------------------|ip/mpls|-------------------------|ip/m= pls| > | node 6| | node 7| =20 > | node 8| > --------- --------- =20 > --------- >=20 > All nodes are connected with 100 Mbps links. >=20 > I try to compare IP and MPLS throughput and RTT, but I got odd results.= =20 > For IP throughput between Source and Destination with netperf, I got=20 > approximately 90 Mbps over 1,2,3,4 and 5 mpls node, but for MPLS=20 > throughput with same tool I got only 350 kbps. What are the MTU's of your links? Did you turn off debugging? Did you recompile with MPLS_DEBUG turned off? > When I ping (ping -qfc 10000 -s 8 dest_ip) Destination from Source, for= =20 > MPLS I got 100 times bigger min/avg/max RTT resutls then for IP. But=20 > for MPLS is faster total ping time then for IP. >=20 > One more problem: Why IP TTL is decrementing when transmitting thruogh=20 > MPLS network. I think that IP TTL must be unchanged in MPLS network. Wrong. Read RFC3031. Is is a user-configurable option. In mpls-linux it is configurable via the 'propagate_ttl' NHLFE option. >=20 > =09 > --------- --------- --------- --------- --------- --------- --------- > | ip | ------|ip/mpls|-------|ip/mpls|-------|ip/mpls|-------|ip/mpls|= -------|ip/mpls|-------| ip | > | node 1| | node 1| | node 2| | node 3| | node 4| | node 5| | node 2| > --------- --------- --------- --------- --------- --------- --------- > | | | > | | | > | | | > --------- --------- --------- > |ip/mpls|-----------------------|ip/mpls|-----------------------|ip/mpl= s| > | node 6| | node 7| | node 8| > --------- --------- --------- PS please make you ascii drawings fit an 80 col terminal. --=20 James R. Leu jl...@mi... |
Thanks for helping keep SourceForge clean.
X